Back
Strong employer brand, metro location, mid-level generalist ML role with broad skills attracts high competition.
Highly specialized enterprise retrieval, vector search, and ACL expertise limits transferability across industries.
Explicit 3+ years requirement plus mandatory production retrieval, vector search, and IR tooling experience.
Login to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Build and own the unified enterprise retrieval layer that integrates multiple SaaS sources like Google Drive, Salesforce, Jira, Zendesk with permission-aware, low-latency, real-time syncing.
Design and implement hybrid retrieval systems combining lexical, dense vector, and structured retrieval with ranking tuned for cross-source, heterogeneous content.
Develop query understanding components (intent parsing, entity linking, LLM-assisted rewriting) and evaluation/monitoring systems to ensure retrieval quality at scale for enterprise AI agents.
3+ years building production search, retrieval, knowledge-base, or recommendation systems (5+ preferred).
Proficiency in backend programming with Python, Go, Java or similar.
Hands-on experience with search engines like OpenSearch, Elasticsearch, Solr or Vespa and strong understanding of IR fundamentals (TF-IDF, BM25, learning-to-rank).
Experience with vector search/embeddings using tools like FAISS, pgvector, Pinecone and familiarity with enterprise ACL/permission models and their enforcement in retrieval.
Senior individual contributor comfortable owning complex, multi-source retrieval architecture with strong rigor in evaluation and engineering discipline.
Experienced working with heterogeneous enterprise data sources and permissions, blending classical IR and modern LLM/NLP methods.
Skilled in pragmatic system design balancing latency, freshness, recall, and operational cost in scalable cloud environments.